implement-and-validate

Name: implement-and-validate
Author: Codagent-AI

28stars1forks

How to install implement-and-validate?

codagent-ai/agent-skills/implement-and-validate

$npx -y skills add Codagent-AI/agent-skills --skill implement-and-validate

Installs into the current project.

Summary

Autonomous implementer agent that executes a single task end-to-end using TDD and verifies with Agent Validator. Activates for requests such as "implement this task", "finish this ticket", "apply this spec end-to-end", or "complete the implementation".

Files · 1

View on GitHub

SKILL.md

1	Implement a single task from start to finish. Verify with self-review and the validator. Return a report.
2
3	## Your Task
4
5	## Implementation Methodology
6
7	Implement the specified task using the `codagent:implement-with-tdd` skill.
8
9	Implement exactly what the task specifies — no extra features, refactoring, or improvements beyond scope. Follow existing code patterns and conventions.
10
11	## Self-Review
12
13	After implementation is complete, perform a structured self-review:
14
15	1. Is every scenario from the task spec implemented?
16	2. Are there any changes not justified by the task spec?
17	3. Are all success criteria met?
18	4. Do all tests and linters pass?
19
20	If self-review finds issues, fix them before proceeding to the validator.
21
22	## Validator Integration
23
24	After self-review passes, run the validator directly using the steps below. Do NOT invoke the `agent-validator:validator-run` skill — follow these instructions instead.
25
26	1. Clean up stale lock (safe — tasks are dispatched sequentially, never in parallel):
27	```bash
28	mkdir -p validator_logs
29	rm -f validator_logs/.validator-run.lock
30	```
31
32	2. Run the validator with output captured to a file (Bun can drop stdout/stderr during LLM review subprocesses, so always redirect to a file):
33	```bash
34	agent-validator run > validator_logs/_subagent-run.log 2>&1; printf 'VALIDATOR_EXIT=%s\n' "$?" >> validator_logs/_subagent-run.log
35	```
36	Use `Bash` with `timeout: 300000` (5 minutes). Do NOT use `run_in_background`.
37
38	3. Read the captured output (this is the reliable path — do not rely on the Bash tool's stdout capture):
39	```bash
40	cat validator_logs/_subagent-run.log
41	```
42
43	CRITICAL: Exit code 1 means "violations were found" — the command ran successfully but detected issues that need fixing. This is NOT an infrastructure failure. Do NOT retry blindly — read the output to understand what needs fixing.
44
45	4. Check the `Status:` line in the output and act accordingly:
46	- `Status: Passed` or `Status: Passed with warnings` → proceed to commit
47	- `Status: Failed` → read the violation details from the output. For each violation:
48	- CHECK failures: follow the fix instructions shown in the output
49	- REVIEW violations: fix the code issue described in the violation. If a violation is clearly a false positive, note it in your report but do not block on it.
50	After fixing, re-run the validator by going back to step 2. Maximum 3 retry attempts.
51	- `Status: Retry limit exceeded` → stop and include the failure details in your report
52	- No `Status:` line found → the output file may be empty (known Bun issue). Read the latest console log instead:
53	```bash
54	ls -t validator_logs/console.*.log 2>/dev/null \| head -1 \| xargs -r cat
55	```
56	If no console log exists either, re-run the command once more (go back to step 2).
57
58	## Commit
59
60	After the validator passes, commit all changes:
61
62	Check if the `commit-commands:commit` skill is available:
63
64	- If `commit-commands:commit` is available → invoke it to perform the commit
65	- If not available → stage all changes (including new files), propose a commit message following the conventional commits format (`<type>: <description>`), then run `git commit -m "<message>"`
66
67	## Blocker Handling
68
69	If you hit a genuine blocker (missing dependency, broken environment, contradictory requirements in the task), return failure immediately with:
70	- What you attempted
71	- What blocked you
72	- Why you cannot proceed
73
74	Do NOT wait for input. Return failure and let the coordinator handle it.
75
76	## Return Report
77
78	When done, return a natural language report containing:
79
80	1. What was implemented: Summary of changes made
81	2. What was tested: Tests written/run and their results
82	3. Files changed: List of files created or modified
83	4. Self-review findings: Any issues found and fixed during self-review
84	5. Questions: Any ambiguities or clarifications needed (if applicable)
85	6. Validator status: "passed" or details on what failed if retry limit was hit
86
87	### Report format for success:
88
89	```
90	## Implementation Report
91
92	### What Was Implemented
93	<summary>
94
95	### Test Results
96	<test details>
97
98	### Files Changed
99	- <file1>
100	- <file2>
101
102	### Self-Review
103	<findings>
104
105	### Validator Status
106	Passed - all gates clear
107	```
108
109	### Report format for failure:
110
111	```
112	## Implementation Report — FAILURE
113
114	### What Was Attempted
115	<summary>
116
117	### Failure Details
118	<what failed and why>
119
120	### Validator Details
121	<which gates passed/failed, what fixes were tried>
122
123	### Blocker Description
124	<the specific blocker preventing completion>
125	```

People who liked this also viewed

6 picks

Type

implement-and-validate

28stars1forks

View on GitHub

How to install implement-and-validate?

codagent-ai/agent-skills/implement-and-validate

$npx -y skills add Codagent-AI/agent-skills --skill implement-and-validate

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	Implement a single task from start to finish. Verify with self-review and the validator. Return a report.
2
3	## Your Task
4
5	## Implementation Methodology
6
7	Implement the specified task using the `codagent:implement-with-tdd` skill.
8
9	Implement exactly what the task specifies — no extra features, refactoring, or improvements beyond scope. Follow existing code patterns and conventions.
10
11	## Self-Review
12
13	After implementation is complete, perform a structured self-review:
14
15	1. Is every scenario from the task spec implemented?
16	2. Are there any changes not justified by the task spec?
17	3. Are all success criteria met?
18	4. Do all tests and linters pass?
19
20	If self-review finds issues, fix them before proceeding to the validator.
21
22	## Validator Integration
23
24	After self-review passes, run the validator directly using the steps below. Do NOT invoke the `agent-validator:validator-run` skill — follow these instructions instead.
25
26	1. Clean up stale lock (safe — tasks are dispatched sequentially, never in parallel):
27	```bash
28	mkdir -p validator_logs
29	rm -f validator_logs/.validator-run.lock
30	```
31
32	2. Run the validator with output captured to a file (Bun can drop stdout/stderr during LLM review subprocesses, so always redirect to a file):
33	```bash
34	agent-validator run > validator_logs/_subagent-run.log 2>&1; printf 'VALIDATOR_EXIT=%s\n' "$?" >> validator_logs/_subagent-run.log
35	```
36	Use `Bash` with `timeout: 300000` (5 minutes). Do NOT use `run_in_background`.
37
38	3. Read the captured output (this is the reliable path — do not rely on the Bash tool's stdout capture):
39	```bash
40	cat validator_logs/_subagent-run.log
41	```
42
43	CRITICAL: Exit code 1 means "violations were found" — the command ran successfully but detected issues that need fixing. This is NOT an infrastructure failure. Do NOT retry blindly — read the output to understand what needs fixing.
44
45	4. Check the `Status:` line in the output and act accordingly:
46	- `Status: Passed` or `Status: Passed with warnings` → proceed to commit
47	- `Status: Failed` → read the violation details from the output. For each violation:
48	- CHECK failures: follow the fix instructions shown in the output
49	- REVIEW violations: fix the code issue described in the violation. If a violation is clearly a false positive, note it in your report but do not block on it.
50	After fixing, re-run the validator by going back to step 2. Maximum 3 retry attempts.
51	- `Status: Retry limit exceeded` → stop and include the failure details in your report
52	- No `Status:` line found → the output file may be empty (known Bun issue). Read the latest console log instead:
53	```bash
54	ls -t validator_logs/console.*.log 2>/dev/null \| head -1 \| xargs -r cat
55	```
56	If no console log exists either, re-run the command once more (go back to step 2).
57
58	## Commit
59
60	After the validator passes, commit all changes:
61
62	Check if the `commit-commands:commit` skill is available:
63
64	- If `commit-commands:commit` is available → invoke it to perform the commit
65	- If not available → stage all changes (including new files), propose a commit message following the conventional commits format (`<type>: <description>`), then run `git commit -m "<message>"`
66
67	## Blocker Handling
68
69	If you hit a genuine blocker (missing dependency, broken environment, contradictory requirements in the task), return failure immediately with:
70	- What you attempted
71	- What blocked you
72	- Why you cannot proceed
73
74	Do NOT wait for input. Return failure and let the coordinator handle it.
75
76	## Return Report
77
78	When done, return a natural language report containing:
79
80	1. What was implemented: Summary of changes made
81	2. What was tested: Tests written/run and their results
82	3. Files changed: List of files created or modified
83	4. Self-review findings: Any issues found and fixed during self-review
84	5. Questions: Any ambiguities or clarifications needed (if applicable)
85	6. Validator status: "passed" or details on what failed if retry limit was hit
86
87	### Report format for success:
88
89	```
90	## Implementation Report
91
92	### What Was Implemented
93	<summary>
94
95	### Test Results
96	<test details>
97
98	### Files Changed
99	- <file1>
100	- <file2>
101
102	### Self-Review
103	<findings>
104
105	### Validator Status
106	Passed - all gates clear
107	```
108
109	### Report format for failure:
110
111	```
112	## Implementation Report — FAILURE
113
114	### What Was Attempted
115	<summary>
116
117	### Failure Details
118	<what failed and why>
119
120	### Validator Details
121	<which gates passed/failed, what fixes were tried>
122
123	### Blocker Description
124	<the specific blocker preventing completion>
125	```

People who liked this also viewed

6 picks

Type